app.py

import gradio as gr
from transformers import pipeline
import numpy as np

transcriber = pipeline(
    "automatic-speech-recognition",
    model="model",
    chunk_length_s=30
)

def transcribe(audio):
    sr, y = audio
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    return transcriber({"sampling_rate": sr, "raw": y})["text"]


demo = gr.Interface(
    transcribe,
    gr.Audio(),
    "text",
    title = "Banking-ASR",
    description = "Please record/upload Banking Queries to Transcribe",
    theme=gr.themes.Soft()
)

demo.launch()